{"total":300,"rows":[{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2404.05961","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","created":"2024-04-09","cited_by_count":404,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2105.02358","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","created":"2021-05-05","cited_by_count":109,"area":null},{"id":"2203.17030","title":"Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks","created":"2022-03-31","cited_by_count":88,"area":null},{"id":"2102.07916","title":"Few-Shot Graph Learning for Molecular Property Prediction","created":"2021-02-16","cited_by_count":81,"area":null},{"id":"2109.04553","title":"Is Attention Better Than Matrix Decomposition?","created":"2021-09-09","cited_by_count":77,"area":null},{"id":"2103.06413","title":"FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders","created":"2021-03-11","cited_by_count":75,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2106.06965","title":"Contrastive Attention for Automatic Chest X-ray Report Generation","created":"2021-06-13","cited_by_count":71,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2204.09269","title":"A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond","created":"2022-04-20","cited_by_count":64,"area":null},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2111.04318","title":"Auto-Encoding Knowledge Graph for Unsupervised Medical Report Generation","created":"2021-11-08","cited_by_count":47,"area":null},{"id":"2203.13611","title":"Class-Incremental Learning for Action Recognition in Videos","created":"2022-03-25","cited_by_count":46,"area":null},{"id":"2207.11995","title":"3D Siamese Transformer Network for Single Object Tracking on Point Clouds","created":"2022-07-25","cited_by_count":44,"area":null},{"id":"2108.06076","title":"PVT: Point-Voxel Transformer for Point Cloud Learning","created":"2021-08-13","cited_by_count":43,"area":null},{"id":"2205.01287","title":"SemAttack: Natural Textual Attacks via Different Semantic Spaces","created":"2022-05-03","cited_by_count":42,"area":null},{"id":"2204.09455","title":"Simplicial Attention Networks","created":"2022-04-20","cited_by_count":41,"area":null},{"id":"2102.09267","title":"Sparse-Interest Network for Sequential Recommendation","created":"2021-02-18","cited_by_count":38,"area":null},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2102.09117","title":"Spatio-Temporal Graph Dual-Attention Network for Multi-Agent Prediction and Tracking","created":"2021-02-18","cited_by_count":35,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2107.07045","title":"Explainable AI: current status and future directions","created":"2021-07-12","cited_by_count":33,"area":null},{"id":"2110.00111","title":"Deep Learning-based Action Detection in Untrimmed Videos: A Survey","created":"2021-09-30","cited_by_count":32,"area":null},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32,"area":null},{"id":"2201.05307","title":"Unsupervised Temporal Video Grounding with Deep Semantic Clustering","created":"2022-01-14","cited_by_count":30,"area":null},{"id":"2204.05845","title":"Probabilistic Compositional Embeddings for Multimodal Image Retrieval","created":"2022-04-12","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","cited_by_count":27,"area":null},{"id":"2309.02138","title":"Generalized Simplicial Attention Neural Networks","created":"2023-09-05","cited_by_count":27,"area":null},{"id":"2106.10446","title":"Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering","created":"2021-06-19","cited_by_count":26,"area":null},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"area":null},{"id":"2201.02797","title":"A Unified Review of Deep Learning for Automated Medical Coding","created":"2022-01-08","cited_by_count":26,"area":null},{"id":"2101.04838","title":"Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition","created":"2021-01-13","cited_by_count":25,"area":null},{"id":"2103.16808","title":"Self-Supervised Euphemism Detection and Identification for Content Moderation","created":"2021-03-31","cited_by_count":25,"area":null},{"id":"2103.09013","title":"Dense Interaction Learning for Video-based Person Re-identification","created":"2021-03-16","cited_by_count":24,"area":null},{"id":"2108.08983","title":"SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2205.07324","title":"Transkimmer: Transformer Learns to Layer-wise Skim","created":"2022-05-15","cited_by_count":24,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2102.04754","title":"Bayesian Transformer Language Models for Speech Recognition","created":"2021-02-09","cited_by_count":22,"area":null},{"id":"2106.03044","title":"Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2107.08031","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","created":"2021-07-16","cited_by_count":21,"area":null},{"id":"2110.05841","title":"Relative Molecule Self-Attention Transformer","created":"2021-10-12","cited_by_count":21,"area":null},{"id":"2203.07485","title":"Simplicial Attention Neural Networks","created":"2022-03-14","cited_by_count":21,"area":null},{"id":"2207.01376","title":"Task Discrepancy Maximization for Fine-grained Few-Shot Classification","created":"2022-07-04","cited_by_count":21,"area":null},{"id":"2107.04082","title":"Improved Language Identification Through Cross-Lingual Self-Supervised Learning","created":"2021-07-08","cited_by_count":20,"area":null},{"id":"2205.10226","title":"Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze?","created":"2022-04-25","cited_by_count":20,"area":null},{"id":"2212.01231","title":"BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks","created":"2022-12-02","cited_by_count":20,"area":null},{"id":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2110.10470","title":"Interpreting Deep Learning Models in Natural Language Processing: A Review","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2103.01863","title":"Data Augmentation for Abstractive Query-Focused Multi-Document Summarization","created":"2021-03-02","cited_by_count":18,"area":null},{"id":"2112.08560","title":"Block-Skim: Efficient Question Answering for Transformer","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2504.10920","title":"Towards Efficient Partially Relevant Video Retrieval with Active Moment Discovering","created":"2025-04-15","cited_by_count":18,"area":null},{"id":"2102.02680","title":"Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection","created":"2021-02-04","cited_by_count":17,"area":null},{"id":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17,"area":null},{"id":"2307.00067","title":"Transformers in Healthcare: A Survey","created":"2023-06-30","cited_by_count":17,"area":null},{"id":"2403.01528","title":"Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey","created":"2024-03-03","cited_by_count":17,"area":null},{"id":"2104.13100","title":"Shellcode_IA32: A Dataset for Automatic Shellcode Generation","created":"2021-04-27","cited_by_count":16,"area":null},{"id":"2105.03070","title":"SpeechNet: A Universal Modularized Model for Speech Processing Tasks","created":"2021-05-07","cited_by_count":16,"area":null},{"id":"2208.09329","title":"Causal Intervention Improves Implicit Sentiment Analysis","created":"2022-08-19","cited_by_count":16,"area":null},{"id":"2101.09499","title":"Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning","created":"2021-01-23","cited_by_count":15,"area":null},{"id":"2112.01047","title":"DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding","created":"2021-12-02","cited_by_count":15,"area":null},{"id":"2302.00907","title":"History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System","created":"2023-02-02","cited_by_count":15,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2103.12258","title":"Hallucination of speech recognition errors with sequence to sequence learning","created":"2021-03-23","cited_by_count":14,"area":null},{"id":"2110.07477","title":"RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models","created":"2021-10-14","cited_by_count":14,"area":null},{"id":"2104.10652","title":"TransICD: Transformer Based Code-wise Attention Model for Explainable ICD Coding","created":"2021-03-28","cited_by_count":13,"area":null},{"id":"2105.07623","title":"Sentence Similarity Based on Contexts","created":"2021-05-17","cited_by_count":12,"area":null},{"id":"2107.05223","title":"BERT-like Pre-training for Symbolic Piano Music Classification Tasks","created":"2021-07-12","cited_by_count":12,"area":null},{"id":"2109.03069","title":"Sequential Diagnosis Prediction with Transformer and Ontological Representation","created":"2021-09-07","cited_by_count":12,"area":null},{"id":"2110.06257","title":"Causal Discovery from Conditionally Stationary Time Series","created":"2021-10-12","cited_by_count":12,"area":null},{"id":"2111.07534","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2112.13310","title":"Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence","created":"2021-12-26","cited_by_count":12,"area":null},{"id":"2108.02352","title":"Understand me, if you refer to Aspect Knowledge: Knowledge-aware Gated Recurrent Memory Network","created":"2021-08-05","cited_by_count":11,"area":null},{"id":"2109.02403","title":"Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction","created":"2021-09-06","cited_by_count":11,"area":null},{"id":"2201.01633","title":"Adaptive Online Incremental Learning for Evolving Data Streams","created":"2022-01-05","cited_by_count":11,"area":null},{"id":"2305.18238","title":"Multi-behavior Self-supervised Learning for Recommendation","created":"2023-05-22","cited_by_count":11,"area":null},{"id":"2308.11780","title":"Few-shot Anomaly Detection in Text with Deviation Learning","created":"2023-08-22","cited_by_count":11,"area":null},{"id":"2310.08232","title":"Language Models are Universal Embedders","created":"2023-10-12","cited_by_count":11,"area":null},{"id":"2102.13419","title":"Iterative SE(3)-Transformers","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2108.00194","title":"Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition","created":"2021-07-31","cited_by_count":10,"area":null},{"id":"2108.12465","title":"Code-switched inspired losses for generic spoken dialog representations","created":"2021-08-27","cited_by_count":10,"area":null},{"id":"2112.11540","title":"Mixed Precision of Quantization of Transformer Language Models for Speech Recognition","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2210.07661","title":"CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling","created":"2022-10-14","cited_by_count":10,"area":null},{"id":"2312.16388","title":"Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding","created":"2023-12-27","cited_by_count":10,"area":null},{"id":"2401.06034","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2405.13985","title":"LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2502.20525","title":"Revisiting Kernel Attention with Correlated Gaussian Process Representation","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2101.07715","title":"Meningioma segmentation in T1-weighted MRI leveraging global context and attention mechanisms","created":"2021-01-19","cited_by_count":9,"area":null},{"id":"2102.08092","title":"An AutoML-based Approach to Multimodal Image Sentiment Analysis","created":"2021-02-16","cited_by_count":9,"area":null},{"id":"2103.12377","title":"Exercise? I thought you said 'Extra Fries': Leveraging Sentence Demarcations and Multi-hop Attention for Meme Affect Analysis","created":"2021-03-23","cited_by_count":9,"area":null}],"next_cursor":"100"}